Stage-wise Fine-tuning for Graph-to-Text Generation

Graph-to-text generation has benefited from pre-trained language models (PLMs) in achieving better performance than structured graph encoders. However, they fail to fully utilize the structure information of the input graph... In this paper, we aim to further improve the performance of the pre-trained language model by proposing a structured graph-to-text model with a two-step fine-tuning mechanism which first fine-tunes the model on Wikipedia before adapting to the graph-to-text generation. In addition to using the traditional token and position embeddings to encode the knowledge graph (KG), we propose a novel tree-level embedding method to capture the inter-dependency structures of the input graph. This new approach has significantly improved the performance of all text generation metrics for the English WebNLG 2017 dataset. read more

PDF Abstract ACL 2021 PDF ACL 2021 Abstract

Datasets


Results from the Paper


 Ranked #1 on Data-to-Text Generation on WebNLG Full (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Data-to-Text Generation WebNLG T5-large + Position + Wiki BLEU 0.6607 # 1
Data-to-Text Generation WebNLG Full T5-large + Position + Wiki BLEU 60.56 # 1

Methods